Hugging Face's logo

gayanin
/
bart-with-asr-noise-del-0.5

Text2Text Generation
Transformers
Safetensors
bart
Generated from Trainer
Inference Endpoints
Model card Files Community
bart-with-asr-noise-del-0.5 / README.md
gayanin's picture
gayanin
Training in progress, step 500
36f97ca verified
preview code
|
raw
history blame
1.49 kB
metadata
license: apache-2.0
base_model: facebook/bart-base
tags:
  - generated_from_trainer
model-index:
  - name: bart-with-asr-noise-del-0.4
    results: []

bart-with-asr-noise-del-0.4

This model is a fine-tuned version of facebook/bart-base on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 1.0343

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 5e-05
  • train_batch_size: 16
  • eval_batch_size: 16
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 10
  • num_epochs: 3

Training results

Training Loss Epoch Step Validation Loss
1.3196 0.62 500 1.1758
1.1351 1.24 1000 1.0880
0.9108 1.86 1500 1.0304
0.7589 2.48 2000 1.0343

Framework versions

  • Transformers 4.37.2
  • Pytorch 2.1.2+cu121
  • Datasets 2.17.1
  • Tokenizers 0.15.2